Marcel A. Croon

Predicting Group-Level Outcome Variables From Variables Measured at the Individual Level: A Latent Variable Multilevel Model

In multilevel modeling, one often distinguishes between macro-micro and micro-macro situations. In a macro-micro multilevel situation, a dependent variable measured at the lower level is predicted or explained by variables measured at that lower or a higher level. In a micro-macro multilevel situation, a dependent variable defined at the higher group level is predicted or explained on the basis of independent variables measured at the lower individual level. Up until now, multilevel methodology has mainly focused on macro-micro multilevel situations. In this article, a latent variable model is proposed for analyzing data from micro-macro situations. It is shown that regression analyses carried out at the aggregated level result in biased parameter estimates. A method that uses the best linear unbiased predictors of the group means is shown to yield unbiased estimates of the parameters.

HRM, Communication, Satisfaction, and Perceived Performance A Cross-Level Test

Employee perceptions of HR practices are often assumed to play an important mediating role in the relationship between HR systems and HR outcomes. In a multisource, multilevel study of 2,063 employees and 449 managers in 119 branches of a single large firm, the authors tested how managers’ perceptions of the HR practices implemented in the unit relate to employee perceptions of these HR practices. The authors’ main aim is to explore managers’ communication quality as a moderator of the relationship between manager-rated and employee-rated HR practices. They also tested whether perceived human resource management (HRM) perceptions in turn relate to perceived unit performance and satisfaction. Multilevel structural equation modeling analyses showed that HRM perceptions mediated the relationship between implemented HRM and both satisfaction and unit performance and that communication moderated the relationship between manager-rated and employee-rated HRM. These findings contribute to scholars’ understanding of how HRM affects employee-related outcomes.

The Multiple Propensity Score as Control for Bias in the Comparison of More Than Two Treatment Arms An Introduction From a Case Study in Mental Health

Background and Objective:The propensity score method (PS) has proven to be an effective tool to reduce bias in nonrandomized studies, especially when the number of (potential) confounders is large and dimensionality problems arise. The PS method introduced by Rosenbaum and Rubin is described in detail for studies with 2 treatment options. Since in clinical practice we are often interested in the comparison of multiple interventions, there was a need to extend the PS method to multiple treatments. It has been shown that in theory a multiple PS method is possible. So far, its practical application is rare and a practical introduction lacking. Methods:A practical guideline to illustrate the use of the multiple PS method is provided with data from a mental health study. The multiple PS is estimated with a multinomial logistic regression analysis. The multiple PS is the probability of assignment to each treatment category. Subsequently, to estimate the treatment effects while controlling for initial differences, the multiple PSs, calculated for each treatment category, are included as extra predictors in the regression analysis. Results:With the multiple PS method, balance was achieved in all relevant pretreatment variables. The corrected estimated treatment effects were somewhat different from the results without control for initial differences. Conclusions:Our results indicate that the multiple PS method is a feasible method to adjust for observed pretreatment differences in nonrandomized studies where the number of pretreatment differences is large and multiple treatments are compared.

Childcare involvement, job characteristics, gender and work attitudes as predictors of emotional exhaustion and sickness absence

Abstract Reports in the literature vary regarding the existence of gender differences in relation to burnout and sickness absence. To investigate this, the present study was aimed at investigating the role of several gender-relevant variables, particularly childcare obligations, job characteristics, and work attitudes in emotional exhaustion and sickness absence in 404 male and female nurses in an institution for people with learning difficulties. Questionnaires were administered reflecting demographic and job characteristics, work and non-work attitudes, and emotional exhaustion (as measured by the Emotional Exhaustion Scale of the Maslach Burnout Inventory). Female nurses were expected to report higher levels of emotional exhaustion and to be absent through sickness more often than men. Also, childcare investment, job characteristics, and (non) work attitudes were expected—via emotional exhaustion—to predict gender differences in sickness absence. It was found that women did not have higher sickness absence rates, and although a gender difference appeared in emotional exhaustion it was in the opposite direction from that predicted. For both genders, emotional exhaustion had a significant positive effect on sickness absence, and especially childcare investment and number of work hours appeared to contribute to both outcomes. These results are of interest because, despite current stereotypes, sickness absence was not higher in women, and neither were women more at risk for emotional exhaustion. In particular, load—workload as well as care load—appeared to predict emotional exhaustion and thus sickness absence.

Operationalising critically reflective work behaviour

Purpose – The purpose of this paper is to operationalise critical reflection. Although critical reflection is widely recognised as a crucial element in individual and organisational learning, not many instruments exist to measure critical reflection in the context of work organisations.Design/methodology/approach – Critical reflection was operationalised by using a combination of a literature review and a survey.Findings – Critically reflective work behaviour was defined as a set of connected activities carried out individually or in interaction with others, aimed at optimising individual or collective practices, or critically analysing and trying to change organizational or individual values. Based on the survey, an instrument was developed for measuring six dimensions of critically reflective work behaviour, namely, critical opinion‐sharing, asking for feedback, challenging group‐think, openness about mistakes, experimentation and career awareness.Research limitations/implications – Future research shou...

The relationships between team learning activities and team performance

Purpose – The purpose of this paper is to investigate how different team learning activities relate to different types of team performance as rated by team members and managers.Design/methodology/approach – The 624 respondents, working in 88 teams in seven different organizations indicate their perceptions of team learning and their performance ratings of the team. Moreover, managers in the organization are asked to evaluate the team performance.Findings – Team member ratings of effectiveness are positively related to the boundedness and stability of the team and information processing and negatively related to information acquisition. Manager ratings of effectiveness are positively related to boundedness and stability, information processing and information storage and retrieval. Team member ratings of efficiency are positively related to information processing and negatively related to information acquisition. Manager ratings of efficiency are positively related to boundedness and stability and informat...

New developments in categorical data analysis for the social and behavioral sciences

Contents: Preface. L.A. van der Ark, M.A. Croon, K. Sijtsma, Statistical Models for Categorical Variables. J.A. Hagenaars, Misclassification Phenomena in Categorical Data Analysis: Regression Toward the Mean and Tendency Toward the Mode. J.K. Vermunt, J. Magidson, Factor Analysis With Categorical Indicators: A Comparison Between Traditional and Latent Class Approaches. O. Laudy, J. Boom, H. Hoijtink, Bayesian Computational Methods for Inequality Constrained Latent Class Analysis. W.P. Bergsma, M.A. Croon, Analyzing Categorical Data by Marginal Models. I. Moustaki, M. Knott, Computational Aspects of the E-M and Bayesian Estimation in Latent Variable Models. P.W. van Rijn, P.C.M. Molenaar, Logistic Models for Single-Subject Time Series. L.A. van der Ark, K. Sijtsma, The Effect of Missing Data Imputation on Mokken Scale Analysis. H. Kelderman, Building IRT Models From Scratch: Graphical Models, Exchangeability, Marginal Freedom, Scale Types, and Latent Traits. T.M. Bechger, G. Maris, H.H.F.M. Verstralen, N.D. Verhelst, The Nedelsky Model For Multiple-Choice Items. K. Draney, M. Wilson, Application of the Polytomous Saltus Model to Stage-Like Proportional Reasoning Data. J-P. Fox, Multilevel IRT Model Assessment.

The impact of organizational changes on psychological contracts: A longitudinal study

Purpose – The purpose of this study is to add to the existing literature on the impact of organizational changes on psychological contracts by examining the exchange between employer and employee obligations and organizational commitment and intention to turnover in a causal model.Design/methodology/approach – Psychological contracts of 450 health care workers were assessed in a three‐wave longitudinal design, covering a one‐year period. The Tilburg Psychological Contract Questionnaire measures perceived obligations with respect to Job Content, Career Development, Social Atmosphere, Organizational Policies and Rewards (perceived organizational obligations) and In‐role and Extra‐role Obligations (perceived employee obligations). Linear structural equation modeling was used to test the changes in psychological contracts and outcome variables over time, and also to investigate the changes in the relationships between the dependent and independent variables over time.Findings – The results show that organizat...

Personality and health habits

Abstract Four hundred and fifty-five males and 523 females from a community sample participated in a study on the relationship between seven health practices (sleeping; breakfasting; snacking; being at good weight; smoking; alcohol consumption and physical activity) and seven personality factors (Neuroticism; Social Inadequacy; Rigidity; Hostility; Self-sufficiency; Dominance and Self-esteem). It was found that the seven health habits did not constitute a homogeneous operationalization of a construct “positive lifestyle.” The intercorrelations between the different health practices were typically low. The results of MANOVAs and subsequent ANOVAs revealed small, but statistically significant differences between subjects reporting positive and those reporting poor health habits. The failure to find significant interactions with sex indicated that the results for males and females were generally similar. Neuroticism and hostility discriminated best between the groups with poor or good health behaviors. This ...

Determinants of general fatigue and emotional exhaustion: a prospective study

The present study was undertaken to determine the factors that predict general fatigue and emotional exhaustion over two years. Because fatigue is hypothesized to be persistent, general fatigue and emotional exhaustion at baseline were included as predictors. A model of mediators and moderators of the stress-health relationship (Taylor and Aspinwall, 1996), was employed to select the other variables. A sample of the Dutch working population (N = 325) completed questionnaires concerning demographic variables, personality and temperament, work pressure and workload, perceived social support, perceived stress, and coping strategies. Emotional exhaustion and general fatigue, measured two years later, were the outcome variables. Structural equation modeling indicated that general fatigue and emotional exhaustion are rather persistent. Furthermore, workload predicted both emotional exhaustion and general fatigue. Finally, emotional exhaustion was predicted by hardiness, whereas general fatigue was predicted by strength of inhibition.